Sampling Training Data for Continual Learning Between Robots and the Cloud

• URL: http://arxiv.org/abs/2012.06739v1
• Date: Sat, 12 Dec 2020 05:52:33 GMT
• Title: Sampling Training Data for Continual Learning Between Robots and the Cloud
• Authors: Sandeep Chinchali, Evgenya Pergament, Manabu Nakanoya, Eyal Cidon, Edward Zhang, Dinesh Bharadia, Marco Pavone, and Sachin Katti
• Abstract summary: We introduce HarvestNet, an intelligent sampling algorithm that resides on-board a robot and reduces system bottlenecks. It significantly improves the accuracy of machine-learning models on our novel dataset of road construction sites, field testing of self-driving cars, and streaming face recognition. It is between 1.05-2.58x more accurate than baseline algorithms and scalably runs on embedded deep learning hardware.
• Score: 26.116999231118793
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Today's robotic fleets are increasingly measuring high-volume video and LIDAR sensory streams, which can be mined for valuable training data, such as rare scenes of road construction sites, to steadily improve robotic perception models. However, re-training perception models on growing volumes of rich sensory data in central compute servers (or the "cloud") places an enormous time and cost burden on network transfer, cloud storage, human annotation, and cloud computing resources. Hence, we introduce HarvestNet, an intelligent sampling algorithm that resides on-board a robot and reduces system bottlenecks by only storing rare, useful events to steadily improve perception models re-trained in the cloud. HarvestNet significantly improves the accuracy of machine-learning models on our novel dataset of road construction sites, field testing of self-driving cars, and streaming face recognition, while reducing cloud storage, dataset annotation time, and cloud compute time by between 65.7-81.3%. Further, it is between 1.05-2.58x more accurate than baseline algorithms and scalably runs on embedded deep learning hardware. We provide a suite of compute-efficient perception models for the Google Edge Tensor Processing Unit (TPU), an extended technical report, and a novel video dataset to the research community at https://sites.google.com/view/harvestnet.

Related papers

• AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registration [69.21282992341007]
  Auto Synth automatically generates 3D training data for point cloud registration. We replace the point cloud registration network with a much smaller surrogate network, leading to a $4056.43$ speedup. Our results on TUD-L, LINEMOD and Occluded-LINEMOD evidence that a neural network trained on our searched dataset yields consistently better performance than the same one trained on the widely used ModelNet40 dataset.
  arXiv  Detail & Related papers  (2023-09-20T09:29:44Z)
• Continual learning autoencoder training for a particle-in-cell simulation via streaming [52.77024349608834]
  upcoming exascale era will provide a new generation of physics simulations with high resolution. These simulations will have a high resolution, which will impact the training of machine learning models since storing a high amount of simulation data on disk is nearly impossible. This work presents an approach that trains a neural network concurrently to a running simulation without data on a disk.
  arXiv  Detail & Related papers  (2022-11-09T09:55:14Z)
• Continual learning on 3D point clouds with random compressed rehearsal [10.667104977730304]
  This work proposes a novel neural network architecture capable of continual learning on 3D point cloud data. We utilize point cloud structure properties for preserving a heavily compressed set of past data.
  arXiv  Detail & Related papers  (2022-05-16T22:59:52Z)
• EffCNet: An Efficient CondenseNet for Image Classification on NXP BlueBox [0.0]
  Edge devices offer limited processing power due to their inexpensive hardware, and limited cooling and computational resources. We propose a novel deep convolutional neural network architecture called EffCNet for edge devices.
  arXiv  Detail & Related papers  (2021-11-28T21:32:31Z)
• Edge-Cloud Polarization and Collaboration: A Comprehensive Survey [61.05059817550049]
  We conduct a systematic review for both cloud and edge AI. We are the first to set up the collaborative learning mechanism for cloud and edge modeling. We discuss potentials and practical experiences of some on-going advanced edge AI topics.
  arXiv  Detail & Related papers  (2021-11-11T05:58:23Z)
• Point Cloud Pre-training by Mixing and Disentangling [35.18101910728478]
  Mixing and Disentangling (MD) is a self-supervised learning approach for point cloud pre-training. We show that the encoder + ours (MD) significantly surpasses that of the encoder trained from scratch and converges quickly. We hope this self-supervised learning attempt on point clouds can pave the way for reducing the deeply-learned model dependence on large-scale labeled data.
  arXiv  Detail & Related papers  (2021-09-01T15:52:18Z)
• Automated Machine Learning Techniques for Data Streams [91.3755431537592]
  This paper surveys the state-of-the-art open-source AutoML tools, applies them to data collected from streams, and measures how their performance changes over time. The results show that off-the-shelf AutoML tools can provide satisfactory results but in the presence of concept drift, detection or adaptation techniques have to be applied to maintain the predictive accuracy over time.
  arXiv  Detail & Related papers  (2021-06-14T11:42:46Z)
• DeepSatData: Building large scale datasets of satellite images for training machine learning models [77.17638664503215]
  This report presents design considerations for automatically generating satellite imagery datasets for training machine learning models. We discuss issues faced from the point of view of deep neural network training and evaluation.
  arXiv  Detail & Related papers  (2021-04-28T15:13:12Z)
• One-step regression and classification with crosspoint resistive memory arrays [62.997667081978825]
  High speed, low energy computing machines are in demand to enable real-time artificial intelligence at the edge. One-step learning is supported by simulations of the prediction of the cost of a house in Boston and the training of a 2-layer neural network for MNIST digit recognition. Results are all obtained in one computational step, thanks to the physical, parallel, and analog computing within the crosspoint array.
  arXiv  Detail & Related papers  (2020-05-05T08:00:07Z)
• Characterizing and Modeling Distributed Training with Transient Cloud GPU Servers [6.56704851092678]
  We analyze distributed training performance under diverse cluster configurations using CM-DARE. Our empirical datasets include measurements from three GPU types, six geographic regions, twenty convolutional neural networks, and thousands of Google Cloud servers. We also demonstrate the feasibility of predicting training speed and overhead using regression-based models.
  arXiv  Detail & Related papers  (2020-04-07T01:49:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.